v1.10.2

What's Changed

• Add system instructions to customize model output.
• Add Deepseek chat model provider
• Support citation format [1,2,3,4] in message box.
• Update Gemini embedding models

New Contributors

• @singleparadox made their first contribution in #719

Full Changelog: v1.10.1...v1.10.2

v1.10.1

What's Changed

• Fix ONNX issues causing transformer models to not work.
• Fix issues with Gemini & Anthropic models
• feat(models): Update Gemini chat models by @ottsch in #705
• feat(api): add streaming support to search route by @OmarElKadri in #703

New Contributors

• @ottsch made their first contribution in #705
• @OmarElKadri made their first contribution in #703

Full Changelog: v1.10.0...v1.10.1

v1.10.0

What's Changed

• Add keep_alive parameter for Ollama models to specify how long models stay in memory.
• Add file uploads, allowing answers to be generated based on uploaded files (PDF, TXT, and DOCX supported for now).
• Add Gemini chat model providers.
• Add meta search agent class to improve maintainability and facilitate focus mode creation.
• Fix UI bugs (wrong colors, content overflowing).
• Add new prompt for generating blog-style answers.
• Update chat model providers and include the latest models.
• Pause the currently playing video in lightbox mode when the user switches to another video.
• Fix bugs related to custom OpenAI handling.
• Ensure only messages belonging to a chat are deleted, instead of all messages.
• Add automatic image and video search functionality.
• Add new settings page with live config refresh.
• Scroll into view only when a user message is sent.
• Remove backend and move all functionality to Next.js routes.
• Add thinking model support.
• Use a standalone build to reduce build sizes (from 1.8GB and 1.6GB to ~220MB).

New Contributors

• @timoa made their first contribution in #466
• @yslinear made their first contribution in #519
• @bart-jaskulski made their first contribution in #523
• @sainadh-d made their first contribution in #548
• @realies made their first contribution in #555
• @hacking-racoon made their first contribution in #531
• @data5650 made their first contribution in #599
• @user1007017 made their first contribution in #631
• @QuietlyChan made their first contribution in #649
• @wellCh4n made their first contribution in #642
• @ShortCipher5 made their first contribution in #655
• @ericdachen made their first contribution in #663

Full Changelog: v1.9.3...v1.10.0

v1.10.0 RC3

What's New

• Removed toast notifications for connection restore.
• Now displays toast notifications when a request is retried.
• Correctly handles server-side WebSocket closures.
• On mobile, shows settings during error to improve troubleshooting.
• Automatically searches for videos and images per query.
• Updated configuration to support custom OpenAI settings via config.toml (settings persist across sessions).
• Handlers have been updated to use the new custom OpenAI configuration.
• Added an empty check to avoid potential errors.
• Updated the markdown-to-jsx dependency.
• Added support for Gemini 2.0 Flash Exp models.
• Introduced a new settings page with live refresh so changes update instantly without needing a page reload

v1.10.0 RC2

What's new

• Added a unified search agent class to reuse the script for each agent.
• Added Gemini chat model and embedding model provider.

Fixes

• Unhandled rejection caused by empty fileIds field.

v1.10.0 RC

What's new

• Added file upload functionality in webSearch focus mode. Currently, if any other search mode is selected other than web search, it will automatically change it to web search (As implementing file uploads in other focus modes is left, it will be added by the meta search agent class which will be introduced in the next version)
• Added keep_alive variable to specify the time for how long the model should be loaded in Ollama (Defaults to '5m')

v1.9.3

What's new

• Automatic focus on opening the site (on mount).

Fixes

• markdown-to-jsx package has been updated to fix issues with unclosed code block causing client side errors.
• The sources for summarization now have a maximum limit of 15 to prevent context errors.
• Downgraded/fixed NodeJS Docker version to prevent build errors caused by mismatch in package files.

v1.9.2

What's new

• Settings menu has been implemented on mobile devices

Fixes

• Delete and new chat button in the navbar have been fixed
• window.location.href is now used for refreshing the page (A new chat with plus button wasn't refreshing since its the same route)
• Custom OpenAI provider has been fixed in video search, image search and suggestions generation.

v1.9.1

Fixes

• Fixed rewrite not working due to duplicate message IDs
• Fix infinite loading if no models configured (for custom OpenAI users)

v1.9.0

What's New

• Add support for using Perplexica via an API endpoint.
• Added URL & PDF searching capabilities.
• Added line output parser with handling for invalid keys.
• Handle unhandled exceptions and rejections for improved stability.
• Added prebuilt Docker images with multi-architecture support and caching to improve build times.
• Integrated support for Llama 3.2.
• Added optimization modes to search agents and search API.
• Enhanced the chat window to only send the initial message when ready.
• Introduced a new discover feature in the app.
• UI enhancements for the library section.
• Added displayName property to providers for better clarity.
• Linked config.toml as a volume in Docker Compose.

Fixes

• Fixed infinite loading by closing socket on unmount.
• Updated the WebSearchAgent to fix typo and optimize prompt handling.
• Fixed issues with unresolved types across various modules.
• Prevent WebSocket errors when not open.
• Fixed the inability to type / in the settings dialog.
• Added a check for empty arrays to avoid client errors on image and video displays.
• Fixed large SearXNG settings file issues.
• Updated build workflows to improve stability and consistency.
• Fixed q search param not working due to WebSocket issues.